Press "Enter" to skip to content

Category: Machine Learning

Anomaly Detection With Python

Published 2018-01-19 by Kevin Feasel

Robert Sheldon continues his SQL Server Machine Learning Series:

As important as these concepts are to working Python and MLS, the purpose in covering them was meant only to provide you with a foundation for doing what’s really important in MLS, that is, using Python (or the R language) to analyze data and present the results in a meaningful way. In this article, we start digging into the analytics side of Python by stepping through a script that identifies anomalies in a data set, which can occur as a result of fraud, demographic irregularities, network or system intrusion, or any number of other reasons.

The article uses a single example to demonstrate how to generate training and test data, create a support vector machine (SVM) data model based on the training data, score the test data using the SVM model, and create a scatter plot that shows the scoring results.

Click through to see the scenario that Robert has laid out as an example.

Comments closed

Non-English Natural Language Processing

Published 2018-01-16 by Kevin Feasel

The folks at BNOSAC have announced a new natural language processing toolkit for R:

BNOSAC is happy to announce the release of the udpipe R package (https://bnosac.github.io/udpipe/en) which is a Natural Language Processing toolkit that provides language-agnostic ‘tokenization’, ‘parts of speech tagging’, ‘lemmatization’, ‘morphological feature tagging’ and ‘dependency parsing’ of raw text. Next to text parsing, the package also allows you to train annotation models based on data of ‘treebanks’ in ‘CoNLL-U’ format as provided at http://universaldependencies.org/format.html.

The package provides direct access to language models trained on more than 50 languages.

Click through to check it out.

Comments closed

Time Series Forecasting With DeepAR

Published 2018-01-10 by Kevin Feasel

Tim Januschowski, et al, introduce DeepAR on AWS:

Today we are launching Amazon SageMaker DeepAR as the latest built-in algorithm for Amazon SageMaker. DeepAR is a supervised learning algorithm for time series forecasting that uses recurrent neural networks (RNN) to produce both point and probabilistic forecasts. We’re excited to give developers access to this scalable, highly accurate forecasting algorithm that drives mission-critical decisions within Amazon. Just as with other Amazon SageMaker built-in algorithms, the DeepAR algorithm can be used without the need to set up and maintain infrastructure for training and inference.

Click through for a product demonstration.

Comments closed

More On Machine Learning Services

Published 2018-01-02 by Kevin Feasel

Ginger Grant continues her Machine Learning Services series with a couple more posts.  First up is on memory allocation:

Enabling Machine Learning Services on SQL Server which I discussed in a previous blog post, requires you to enable external scripts.  Machine Learning Services are run as external processes to SQLPAL. This means that when you are running Python or R code you are running it outside of the managed processes of SQL Server and SQLPAL.  This design means that the resources used to run Machine Learning Services will run outside of the resources allocated for SQL Server.  If you are planning on using Machine Learning Services you will want to review the server memory options which you may have set for SQL Server.  If you have set the max server memory For example, if your server has 16 GB of RAM memory, and you have allocated  8 GB to SQL Server and you estimate that the operating system will use an additional 4 GB, that means that machine learning services will have 4 GB remaining which it can use.

By design, Machine Learning Services will not starve out all of the memory for SQL Server because it doesn’t use it.  This means DBAs to not have to worry about SQL Server processes not running because some R program is using all the memory as it does not use the memory SQL Server has allocated.  You do have to worry about the amount of memory allocated to Machine Learning Services as by default, using our previous example where there was 4 GB which Machine Learning Services can use, it will only use 20% of the available memory or  819 KB of memory.  That  is not a lot of memory.  Most likely if you are doing a lot of Machine Learning Services work you will want to use more memory which means you will want to change the default memory allocation for external services.

Ginger also talks about the Launchpad service:

When calling external processes, internally SQL Server uses User IDs to call the Launchpad service, which is installed as part of Machine Learning Services and must be running for SQL Server to be able to execute code written in R or Python.  The number of users is set by default.  To change the number of users, open  up SQL Server Configuration Manager by typing SQLServerManager14.msc at the run prompt. For some unknowable reason Microsoft decided to hide this application which was previously available by looking at the installed programs on the server.  Now for some reason they think everyone should memorize this obscure command. Once you have the SQL Server Configuration Manager open, right click on the SQL Server Launchpad service and select the properties which will show the window, as shown below.  You will notice I am running an instance called SQLServer2017 which is listed in parenthesis in the window name.

Both are worth reading.

Comments closed

Python Data Frames In ML Services

Published 2017-12-19 by Kevin Feasel

Robert Sheldon continues his SQL Server Machine Learning Services series by looking at Python data frames:

This article focuses on using data frames in Python. It is the second article in a series about MLS and Python. The first article introduced you briefly to data frames. This article continues that discussion, describing how to work with data frame objects and the data within those objects.

Data frames and the functions they support are available to MLS and Python through the pandas library. The library is available as a Python module that provides tools for analyzing and manipulating data, including the ability to generate data frame objects and work with data frame data. The pandas library is included by default in MLS, so the functions and data structures available to pandas are ready to use, without having to manually install pandas in the MLS library.

There’s quite a bit to this article, making it an interesting read.

Comments closed

Image Counts For Neural Network Training

Published 2017-12-15 by Kevin Feasel

Pete Warden shares his rule of thumb for how many images you need to train a neural network:

In the early days I would reply with the technically most correct, but also useless answer of “it depends”, but over the last couple of years I’ve realized that just having a very approximate rule of thumb is useful, so here it is for posterity:

You need 1,000 representative images for each class.

Like all models, this rule is wrong but sometimes useful. In the rest of this post I’ll cover where it came from, why it’s wrong, and what it’s still good for.

Read on to learn where the number 1000 came from and get some good hints, like flipping and rescaling images.

Comments closed

Capsule Neural Networks

Published 2017-12-14 by Kevin Feasel

Saurabh Kulshrestha covers the topic of capsule neural networks:

This is the problem with Convolutional Neural Networks as well. CNN is good at detecting features, but will wrongly activate the neuron for face detection. This is because it is less effective at exploring the spatial relationships among features.

A simple CNN model can extract the features for nose, eyes and mouth correctly but will wrongly activate the neuron for the face detection. Without realizing the mis-match in spatial orientation and size, the activation for the face detection will be too high.

Read on to see how capsule networks can help solve issues with convolutional neural networks.

Comments closed

Creating An Azure Chat Bot

Published 2017-12-14 by Kevin Feasel

Dustin Ryan shows how to build a QnA bot:

After you’ve created your knowledge base you can then edit and update your knowledge base. There’s a few different ways to update your knowledge.

a. Manually edit the knowledge base directly within QnAMaker.ai. You can do this by directly editing the questions by modifying the text of your knowledge base.

b. Edit the source of your knowledge base. Click the Settings tab on the left to edit the URL of your FAQs or upload a new document.

Building a bot is pretty easy, and Dustin shows you just how to do it.

Comments closed

Estimating Used Car Prices

Published 2017-12-07 by Kevin Feasel

Kevin Jacobs wants to estimate the value of his car and shows how to set up a machine learning job to do this:

As you can see, I collected the brand (Peugeot 106), the type (1.0, 1.1, …), the color of the car (black, blue, …) the construction year of the car, the odometer of the car (which is the distance in kilometers (km) traveled with the car at this point in space and time), the ask price of the car (in Euro’s), the days until the MOT (Ministry of Transport test, a required periodical check-up of your car) and the horse power (HP) of the car. Feel free to use your own variables/units!

It’s an interesting example of how you can approach a real problem.

Comments closed

Introduction To Neural Nets

Published 2017-12-07 by Kevin Feasel

Ben Gorman has a two-part series introducing neural networks.  First, the basics behind neural networks:

We can solve both of the above issues by adding an extra layer to our perceptron model. We’ll construct a number of base models like the one above, but then we’ll feed the output of each base model as input into another perceptron. This model is in fact a vanilla neural network. Let’s see how it might work on some examples.

Then, he digs into the mathematics of backpropagation:

Our problem is one of binary classification. That means our network could have a single output node that predicts the probability that an incoming image represents stairs. However, we’ll choose to interpret the problem as a multi-class classification problem – one where our output layer has two nodes that represent “probability of stairs” and “probability of something else”. This is unnecessary, but it will give us insight into how we could extend task for more classes. In the future, we may want to classify {“stairs pattern”, “floor pattern”, “ceiling pattern”, or “something else”}.

Our measure of success might be something like accuracy rate, but to implement backpropagation (the fitting procedure) we need to choose a convenient, differentiable loss function like cross entropy. We’ll touch on this more, below.

This is definitely a series to read after you’ve gotten your coffee.

Comments closed